Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3552 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.4274. Min Act: -0.0001

Data Index: 72633 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.4534. Min Act: -0.0001

Data Index: 1100302 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.4088. Min Act: -0.0001

Data Index: 637633 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3878. Min Act: -0.0001

Data Index: 1324715 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.4175. Min Act: -0.0001

Data Index: 1216448 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3795. Min Act: -0.0001

Data Index: 163586 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.4311. Min Act: -0.0001

Data Index: 676022 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3930. Min Act: -0.0001

Data Index: 741962 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3899. Min Act: -0.0001

Data Index: 343988 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3694. Min Act: -0.0001

Data Index: 266451 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3915. Min Act: -0.0001

Data Index: 906424 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3875. Min Act: -0.0001

Data Index: 894496 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3768. Min Act: -0.0001

Data Index: 1048251 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3255. Min Act: -0.0001

Data Index: 786822 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3594. Min Act: -0.0001

Data Index: 335065 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3687. Min Act: -0.0001

Data Index: 1136512 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3856. Min Act: -0.0001

Data Index: 1357327 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3578. Min Act: -0.0001

Data Index: 377426 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3529. Min Act: -0.0001

Data Index: 994721 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 0.4534. Min Range: -0.4534

Max Act: 0.3786. Min Act: -0.0001

Data Index: 484058 (C4 (Web Text))

Max Activating Token Index: 417